© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6622
    Prev
    Next
    INDEX
    Explanations

    handling potential errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebel
    1.29
    Anda
    1.18
     colore
    1.13
     pê
    1.13
     yng
    1.11
    に向け
    1.09
    ження
    1.09
     }{
    1.08
     odu
    1.06
     aves
    1.05
    POSITIVE LOGITS
     Dealers
    1.67
     Suga
    1.62
     Tencent
    1.60
     BCCI
    1.60
     dealerships
    1.59
     dealers
    1.57
     accelerators
    1.54
     researcher
    1.53
     robustness
    1.53
     liquidity
    1.53
    Activations Density 0.022%

    No Known Activations